The first neural machine translation system for the Erzya language
Abstract
We present the first neural machine translation system for translation between the endangered Erzya language and Russian and the dataset collected by us to train and evaluate it. The BLEU scores are 17 and 19 for translation to Erzya and Russian respectively, and more than half of the translations are rated as acceptable by native speakers. We also adapt our model to translate between Erzya and 10 other languages, but without additional parallel data, the quality on these directions remains low. We release the translation models along with the collected text corpus, a new language identification model, and a multilingual sentence encoder adapted for the Erzya language. These resources will be available at https://github.com/slone-nlp/myv-nmt.
Keywords
Cite
@article{arxiv.2209.09368,
title = {The first neural machine translation system for the Erzya language},
author = {David Dale},
journal= {arXiv preprint arXiv:2209.09368},
year = {2022}
}
Comments
Accepted to the Field Matters workshop at the COLING 2022 conference